Signals 4 · free daily AI digest

Return or Revise? Learning When Revision Helps Retrieval-Augmented QA

Paper recorded by Signals 4 on 2026-09-24 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-24 on arXiv · recorded by Signals 4 on 2026-09-25

Category: cs.CL · 自然语言处理 · first seen 2026-09-25

Abstract

We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we grade both the returned draft and its candidate revision under the same correctn

Read on arXiv →

#10 most recent of 252 cs.CL papers we have recorded · ↑ newer: PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LL · ↓ older: A Native-Reference Phone-Class Geometry for Second-Language Pronunciat
Cite this page: Return or Revise? Learning When Revision Helps Retrieval-Augmented QA: the #10 most recent of 252 cs.CL papers we have recorded (as of 2026-09-24). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/return-or-revise-learning-when-revision-helps-retrieval-augmented-qa.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions